Content area

Abstract

Artificial intelligence (AI) has been integrated into modern clinical decision support systems and demonstrated expert-level performance across various domains, assisting with tasks of disease diagnosis/prognosis, drug discovery, and personalized treatment. As such applications have quickly proliferated in past decades, the effectiveness of AI tools, however, is contingent upon the quantity and quality of the training data fed into the AI models. In contrast to general domains such as natural image recognition and object detection, where large, well-curated datasets like ImageNet and COCO are available, the healthcare domain is often plagued by various data challenges that often involve a mixture of multiple data issues including data scarcity, imbalance, lack of diversity, and more. Blindly applying ML tools developed in general domains to healthcare without accounting these limitations can lead to serious consequences, such as misdiagnosis, delayed treatment, or even patient harm.

This thesis presents a set of contributions aimed at addressing these data challenges that support more stable and safer AI deployment, with a focus on: Tackling Training on Small Data: Given the limited availability of annotated medical data and the data-intensive nature of AI models, we develop a transfer learning technique that mitigates the domain discrepancy between natural and medical images, thereby enabling more effective learning from small medical datasets. Enable Learning from Distributed Private Data: Observing that healthcare data are naturally distributed, we investigate federated learning in medical images and clinical texts and confirm its effectiveness in learning from distributed data holders without data sharing. Improving Learning from Biased Data: Acknowledging that real-world medical data often exhibit various forms of bias, we propose a novel, exact continuous reformulation for direct metric optimization that offers more precise control over target metrics and facilitates learning towards unbiased metrics. Safeguard AI Model Predictions: noticing that AI is not flawless, we permit prediction slackness by allowing prediction abstention (i.e., rejection) based on designed confidence score under real-world perturbations. Altogether, these contributions seek to advance AI integration in healthcare by ensuring the development of models that are both safe and reliable.

Details

1010268
Business indexing term
Title
Towards Robust and Reliable Artificial Intelligence in Healthcare
Author
Number of pages
156
Publication year
2025
Degree date
2025
School code
0130
Source
DAI-A 87/2(E), Dissertation Abstracts International
ISBN
9798291504017
Advisor
Committee member
Zhang, Rui; Varatharajah, Yogatheesan; Kuang, Rui
University/institution
University of Minnesota
Department
Computer Science
University location
United States -- Minnesota
Degree
Ph.D.
Source type
Dissertation or Thesis
Language
English
Document type
Dissertation/Thesis
Dissertation/thesis number
32170198
ProQuest document ID
3241128595
Document URL
https://www.proquest.com/dissertations-theses/towards-robust-reliable-artificial-intelligence/docview/3241128595/se-2?accountid=208611
Copyright
Database copyright ProQuest LLC; ProQuest does not claim copyright in the individual underlying works.
Database
ProQuest One Academic